Classification and Segmentation of Brain Tumor Using EfficientNet-B7 and U-Net

Antonius Fajar Adinegoro

Department of Physics, Udayana University, Bali, Indonesia.

Gusti Ngurah Sutapa

Department of Physics, Udayana University, Bali, Indonesia.

Anak Agung Ngurah Gunawan *

Department of Physics, Udayana University, Bali, Indonesia.

Ni Kadek Nova Anggarani

Department of Physics, Udayana University, Bali, Indonesia.

Putu Suardana

Department of Physics, Udayana University, Bali, Indonesia.

I. Gde Antha Kasmawan

Department of Physics, Udayana University, Bali, Indonesia.

*Author to whom correspondence should be addressed.


Abstract

Tumors are caused by uncontrolled growth of abnormal cells. Magnetic Resonance Imaging (MRI) is modality that is widely used to produce highly detailed brain images. In addition, a surgical biopsy of the suspected tissue (tumor) is required to obtain more information about the type of tumor. Biopsy takes 10 to 15 days for laboratory testing. Based on a study conducted by Brady in 2016, errors in radiology practice are common, with an estimated daily error rate of 3-5%. Therefore, using the application of artificial intelligence, is expected to simplify and improve the accuracy of doctor's diagnose.

Keywords: Convolutional neural network, U-Net, EfficientNet-B7, machine learning, brain tumor


How to Cite

Adinegoro, Antonius Fajar, Gusti Ngurah Sutapa, Anak Agung Ngurah Gunawan, Ni Kadek Nova Anggarani, Putu Suardana, and I. Gde Antha Kasmawan. 2023. “Classification and Segmentation of Brain Tumor Using EfficientNet-B7 and U-Net”. Asian Journal of Research in Computer Science 15 (3):1-9. https://doi.org/10.9734/ajrcos/2023/v15i3320.

Downloads

Download data is not yet available.